Investigating the working principle of the recommending system and designing a personal music recommending system

This paper, Investigating the Working Principle of the Recommending System and Designing a Personal Music Recommending System, delves into the intricacies of recommendation systems, with a specific focus on music. It begins by exploring the fundamental principles that underpin recommendation systems.The latter part of the paper presents the design of a novel personal music recommendation system. This system leverages the results of K-means clustering to provide faster personalized music recommendations. It considers various auditory factors such as valence (the musical positiveness conveyed by a track), duration (the length of the track), and energy (a measure from 0.0 to 1.0 and represents a perceptual measure of intensity and activity). These factors are calculated by Spotify and made available in an open data set. This research contributes significantly to the field by providing a deeper understanding of recommendation systems and proposing an innovative solution for personalized music recommendations. The novelty of this system lies in its use of K-means clustering and the specific auditory factors it considers, which sets it apart from existing systems.